© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7322
    Prev
    Next
    INDEX
    Explanations

    success or failure status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    1.60
    ig
    1.45
     cuales
    1.43
    슨
    1.29
    åk
    1.28
     salido
    1.26
    ָד
    1.23
    ic
    1.23
    żenie
    1.22
    irme
    1.21
    POSITIVE LOGITS
    ر
    1.87
    transferases
    1.63
    𝑁
    1.53
     chromosomes
    1.53
     exacting
    1.52
    𝑂
    1.52
    𝑚
    1.49
    它
    1.48
    nales
    1.46
    री
    1.42
    Activations Density 0.004%

    No Known Activations